IST Austria Distributed Algorithms and Systems Lab

university

https://ist.ac.at/en/research/alistarh-group/

https://github.com/IST-DASLab

AI & ML interests

None defined yet.

Recent Activity

anm2211 new activity about 1 hour ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:Will bf16 weights be available?

anm2211 new activity about 17 hours ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:What is the SWE Verfied of the the pure GSQ RCO non coder Q3_S

anm2211 new activity about 17 hours ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_S

View all activity

Papers

GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

View all Papers

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF about 1 hour ago

Will bf16 weights be available?

#5 opened about 9 hours ago by

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF about 17 hours ago

What is the SWE Verfied of the the pure GSQ RCO non coder Q3_S

#2 opened 1 day ago by

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF about 17 hours ago

IQ3_S

#26 opened 1 day ago by

DzmitryTheOtherOne

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF about 21 hours ago

Using Chinese causes its reasoning to completely collapse. And a solution that may be more flexible

#4 opened about 23 hours ago by

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF 1 day ago

Could we have a IQ3_S for coder?

#3 opened 1 day ago by

updated a model 1 day ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

Image-Text-to-Text • 117B • Updated 1 day ago • 5.52k • 73

updated a collection 1 day ago

GSQ-RCO-GGUF

Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form • 3 items • Updated 1 day ago • 43

published a model 1 day ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

Image-Text-to-Text • 117B • Updated 1 day ago • 5.52k • 73

updated a model 2 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated 1 day ago • 503k • 342

updated a model 4 days ago

ISTA-DASLab/Qwen3.8-27B-NVFP4-prefiller

24B • Updated 4 days ago • 301 • 17

updated a model 7 days ago

ISTA-DASLab/Qwen3.8-27B-NVFP4-prefiller

24B • Updated 4 days ago • 301 • 17

published a model 8 days ago

ISTA-DASLab/Qwen3.8-27B-NVFP4-prefiller

24B • Updated 4 days ago • 301 • 17

in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 9 days ago

Swift-Qwen3.8-27B-GGUF - is it possible to quantize this model?

#37 opened 14 days ago by

in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 10 days ago

Could you release an uncensored version?

#41 opened 11 days ago by

Anyone unable to load the model on LLama.cpp?

#38 opened 12 days ago by

Iloveprogramming342

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 10 days ago

IQ3_XXS transformer + higher-precision Q8/BF16 n-gram in system RAM?

#15 opened 11 days ago by

MTP support?

#3 opened 13 days ago by

in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 10 days ago

GSQ-RCO-GGUF

#30 opened 17 days ago by

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 10 days ago

Just appreciation, nothing to see here

#13 opened 11 days ago by

Personal test summary — it falls short of the official version in performance, but is excellent as an IQ3 quantization.

#14 opened 11 days ago by